zomato_search

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description bears full responsibility for behavioral disclosure, and it does so thoroughly. It reveals pagination mechanics (opaque cursor, ~12 restaurants per page, next_cursor, has_more termination), the difference between paginated city-wide results and a single unpaginated keyword result set, and the exact set of fields each restaurant carries. This goes well beyond a basic read operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but dense with essential information, front-loaded with the core purpose. It covers pagination, mode differences, filters, and return fields. Slight redundancy exists ('optionally filtered by a keyword' and later 'with a query...') but the information is well organized and every sentence contributes meaningful detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity—5 parameters, two distinct search modes, no output schema or annotations—the description covers all critical aspects: required city slug, pagination protocol, filter applicability, return fields, and how the results connect to sibling endpoints. An agent has enough context to invoke the tool correctly and interpret results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds meaningful inter-parameter context: cursor carries its own sort/pure_veg selection and should be passed alone, sort and pure_veg apply only when query is omitted, and query changes the response structure. This is genuine added value beyond the schema definitions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action and resource: 'Search Zomato restaurants in a city.' It clearly identifies the two modes (city-wide listing vs keyword search) and what each returns. The final sentence ties returned restaurant URLs to the separate restaurant and menu endpoints, distinguishing this tool from siblings like zomato_restaurant and zomato_restaurant_menu.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use each mode: omit query for the city-wide listing, include query for keyword search. It explains cursor pagination and when to pass it, plus which filters apply only to the city-wide listing. It does not explicitly name alternative tools or state conditions for preferring them, though it implies downstream use of restaurant/menu endpoints.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.